© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 22513
    Prev
    Next
    INDEX
    Explanations

    words related to competitive sports and match outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    430
    +0.14
    0.6%
    555
    +0.11
    0.5%
    350
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    555
    +0.14
    0.03
    350
    +0.11
    0.03
    375
    +0.09
    0.02
    Negative Logits
    pmwiki
    -0.81
    bell
    -0.80
    seys
    -0.78
    Activity
    -0.77
    Birth
    -0.74
    warming
    -0.71
    dyl
    -0.69
    mun
    -0.67
    leasing
    -0.67
     Journals
    -0.67
    POSITIVE LOGITS
     fellow
    1.00
     opponent
    0.96
     opponents
    0.86
     him
    0.86
     challenger
    0.82
     whoever
    0.81
     hordes
    0.79
     Manuel
    0.79
     Denis
    0.78
     Sonny
    0.77
    Activations Density 0.135%

    No Known Activations